Reproduce “PosterMate: Audience-driven Collaborative Persona Agents for Poster Design” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Donghoon Shin, Daniel Lee, Gary Hsieh, Gromit Yeuk-Yin Chan
PosterMate leverages generative AI to create collaborative persona agents, simulating diverse target audiences who provide feedback and engage in moderated discussions directly within a poster design canvas. This system helps designers capture overlooked viewpoints and streamline iterations, resulting in designs that are more aligned with marketing objectives.
Key insights
- AI-powered persona agents, constructed from marketing briefs, can effectively simulate diverse and specific audience feedback, proving highly useful and engaging for designers.
- Moderated, multi-agent discussions can effectively synthesize conflicting design feedback into actionable conclusions, leading to outcomes that satisfy a majority of simulated personas.
- Integrating AI as a supportive assistant with direct feedback previews and discussion rationales preserves user agency while streamlining the design iteration process.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.